CTA-Net: A CNN-Transformer Aggregation Network for Improving Multi-Scale Feature Extraction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913547409162240 |
|---|---|
| author | Meng, Chunlei Yang, Jiacheng Lin, Wei Liu, Bowen Zhang, Hongda ouyang, chun Gan, Zhongxue |
| author_facet | Meng, Chunlei Yang, Jiacheng Lin, Wei Liu, Bowen Zhang, Hongda ouyang, chun Gan, Zhongxue |
| contents | Convolutional neural networks (CNNs) and vision transformers (ViTs) have become essential in computer vision for local and global feature extraction. However, aggregating these architectures in existing methods often results in inefficiencies. To address this, the CNN-Transformer Aggregation Network (CTA-Net) was developed. CTA-Net combines CNNs and ViTs, with transformers capturing long-range dependencies and CNNs extracting localized features. This integration enables efficient processing of detailed local and broader contextual information. CTA-Net introduces the Light Weight Multi-Scale Feature Fusion Multi-Head Self-Attention (LMF-MHSA) module for effective multi-scale feature integration with reduced parameters. Additionally, the Reverse Reconstruction CNN-Variants (RRCV) module enhances the embedding of CNNs within the transformer architecture. Extensive experiments on small-scale datasets with fewer than 100,000 samples show that CTA-Net achieves superior performance (TOP-1 Acc 86.76\%), fewer parameters (20.32M), and greater efficiency (FLOPs 2.83B), making it a highly efficient and lightweight solution for visual tasks on small-scale datasets (fewer than 100,000). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11428 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CTA-Net: A CNN-Transformer Aggregation Network for Improving Multi-Scale Feature Extraction Meng, Chunlei Yang, Jiacheng Lin, Wei Liu, Bowen Zhang, Hongda ouyang, chun Gan, Zhongxue Computer Vision and Pattern Recognition Artificial Intelligence Convolutional neural networks (CNNs) and vision transformers (ViTs) have become essential in computer vision for local and global feature extraction. However, aggregating these architectures in existing methods often results in inefficiencies. To address this, the CNN-Transformer Aggregation Network (CTA-Net) was developed. CTA-Net combines CNNs and ViTs, with transformers capturing long-range dependencies and CNNs extracting localized features. This integration enables efficient processing of detailed local and broader contextual information. CTA-Net introduces the Light Weight Multi-Scale Feature Fusion Multi-Head Self-Attention (LMF-MHSA) module for effective multi-scale feature integration with reduced parameters. Additionally, the Reverse Reconstruction CNN-Variants (RRCV) module enhances the embedding of CNNs within the transformer architecture. Extensive experiments on small-scale datasets with fewer than 100,000 samples show that CTA-Net achieves superior performance (TOP-1 Acc 86.76\%), fewer parameters (20.32M), and greater efficiency (FLOPs 2.83B), making it a highly efficient and lightweight solution for visual tasks on small-scale datasets (fewer than 100,000). |
| title | CTA-Net: A CNN-Transformer Aggregation Network for Improving Multi-Scale Feature Extraction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2410.11428 |